pnpm-dependency-upgrade-audit
Pass
Audited by Gen Agent Trust Hub on Aug 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands including
pnpm outdated,pnpm view,pnpm peers check, andrg(ripgrep) to gather information about dependencies and code usage. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests data from untrusted sources such as
package.json,pnpm-workspace.yaml, and source code files searched viarg. - Ingestion points: Reads dependency manifests (
package.json), workspace configurations (pnpm-workspace.yaml), and repository source code (results fromrgsearches). - Boundary markers: The instructions lack explicit delimiters or warnings to treat ingested file content as untrusted data rather than instructions.
- Capability inventory: The agent has the capability to execute shell commands (
pnpm,rg,date) and read arbitrary files within the repository. - Sanitization: There is no evidence of sanitization, validation, or escaping of the content read from external files before it is processed by the agent.
Audit Metadata